SShogo Bench

Gemini 3.8 Flash vs Muse Spark 1.3

Gemini 3.8 Flash leads Muse Spark 1.3 by 1.5 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 3.8 Flash wins 4 and Muse Spark 1.3 wins 12 of 17 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 3.8 FlashMuse Spark 1.3
Agentic coding6360
Long-horizon autonomy6464
Knowledge-work agents4745
Computer use4443
Security & context learning5353

Shared benchmarks

BenchmarkGemini 3.8 FlashMuse Spark 1.3
APEX-Agentsindex64.3%58.6%
FrontierSWEindex19.6%25.8%
CursorBenchindex39.6%41.6%
Chess Puzzles58.0%37.0%
CritPt18.3%26.0%
DTBench95.7%96.5%
FrontierMath Tier 422.0%46.3%
FrontierMath Tiers 1-368.4%74.4%
GeoBench86.0%86.0%
LMCA52.9%53.9%
MirrorCode38.9%54.4%
OTIS Mock AIME98.9%99.2%
ProofBench48.0%58.0%
SciCode56.6%59.7%
SimpleBench82.4%81.8%
WebDev Arena15681652
WeirdML v37.4%6.7%

Specs and price

Gemini 3.8 FlashMuse Spark 1.3
Agent Index56.2 (#21)54.7 (#28)
Agent $/M$0.35$0.030
Input / output $/M$0.75 / $3.75$0.10 / $0.20
Context1M1M
ReleasedSep 2, 2026Sep 2, 2026
WeightsClosedClosed
API hosts62

Don’t pick one. Route.

Shogo can run Gemini 3.8 Flash and Muse Spark 1.3 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo